Plugin

Standards-based OIDC identity, enterprise API-key binding, declarative branding, and OpenAI-compatible model integration for DeepSeek Harness

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota runway forecast, safe resets, web search, image generation, and Fast mode.

Web search provider for the ctx.web seam that routes the DeepSeek web_search tool through a LiteLLM proxy using the OpenAI Responses API, reusing LITELLM_API_KEY.

Image generation workbench and agent tool for DSH: one tool (ark9_generate_image) paints text-to-image and image-to-image via any OpenAI-compatible API. Channels are entirely user-configured - no bundled endpoint, you bring your own baseURL, key and model name (manual input supported). Agent-initiated generations are approval-gated by default: requests queue in the floating panel and nothing bills until you approve; approval is non-blocking (the agent replies "awaiting your approval" immediately, and results, denials or timeouts are injected back so the agent reports them in the next turn). Floating glass workbench with five tabs (Generate / Approvals / Prompts / History / About), aspect-ratio grid with quality-budget + 16px-alignment sizing, transparent background, batch up to 10 images as aggregated sub-tasks, prompt library with custom JSON sources fetched through a host proxy, persistent generation logs with one-click retry, multi-channel aggregation with per-channel model fetching, bilingual UI (zh/en), stroke-SVG icon set, config import/export. Registers as a Better Sidebar tab when dsh-better-sidebar is installed; stacks above the dsh-cua FAB when both are present.

Neutralize tool calls with invalid JSON arguments on the wire so one malformed model generation cannot brick a session against strict OpenAI-compatible servers.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Optimized fork of dsh-image-gen with batch generation (count), gallery pagination, lazy loading, fetch retry/timeout, and 7 providers: Gemini/OpenAI/Seedream/DashScope/Agnes/GLM-Image/Stability AI.

Text-to-video and image-to-video generation via DashScope Wanx, Volcengine Seedance, Google Veo and OpenAI Sora, with tool results saved to the session workspace and a video gallery (grid, lightbox, download, delete) that survives DSH restarts.

Routes the harness through the OpenLLM gateway: a pure-config Cordis patch that adds an `openllm` provider to the in-box pi-ai adapter pointed at the local daemon (`127.0.0.1:8787/v1`, no API key held by dsh) and registers the `openllm mcp` stdio server (openllm, claude-context, supermemory tool groups).

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

Manages the default DSH model, provider and model visibility, and optional OpenAI Responses web search.

DeepSeek Harness vision plugin: 8 analysis modes (describe, OCR, chart data, UI review, object detection, compare, code-gen, debug), any OpenAI- or Anthropic-compatible vision API, with a built-in free vision model and automatic rate-limit failover.

Text-to-image and image-to-image generation inside DSH through OpenAI-compatible endpoints, with an agent tool, multi-provider fallback, and a side-panel workspace with history.

DeepSeek Harness (DSH) plugin that delegates coding tasks to the Claude Code and Codex agent CLIs and streams the whole run live — autonomous control, multi-account, automatic install, git worktrees, and any Anthropic-compatible endpoint.

DSH web search and Responses native V2 compaction for Sub2API-proxied or NewAPI-relayed GPT models

Audio Copilot for DeepSeek Harness: transcribe audio (ASR) and synthesize speech (TTS) — gives text-only agents ears and a voice. Windows-local SAPI TTS out of the box; OpenAI-compatible ASR/TTS endpoints configurable. Includes an in-composer voice-input

Plugin di compatibilità per DeepSeek Harness verso gateway di terze parti in stile OpenAI: tollera stream SSE che si chiudono senza il sentinella [DONE] al termine di una risposta completa.

Wrapper dell'interfaccia a riga di comando OpenAI Codex: esecuzione one-shot, revisione del repository e ripresa della sessione con una sandbox predefinita in sola lettura.

Centro di utilizzo Web DSH con cronologia locale su SQLite, HUD e dashboard, snapshot di account/quota Hub, prezzi personalizzati e registro delle tariffe, ed esportazione CSV/JSON, più OAuth per i coding-plan e un gateway opzionale OpenAI/Anthropic su loopback.

Plugin multimodale per DeepSeek Harness: comprende le immagini e genera immagini tramite endpoint compatibili con OpenAI o DashScope configurabili.

Bundle provider DIT.ai per DeepSeek Harness: installa 29 modelli OpenAI Chat Completions e 10 modelli Anthropic Messages da un unico DIT_API_KEY, con configurazione del pensiero specifica per protocollo.

Ponte per gli allegati immagine nella chat con uno strumento view_image per qualsiasi VLM compatibile OpenAI (Ollama locale o cloud): le immagini incollate/trascinate diventano marcatori di percorso view_image prima di raggiungere i modelli DeepSeek solo testo.

Strumento image_describe (识图) rivolto al modello sull'API compatibile OpenAI di DashScope (qwen3.7-flash), più un ponte di incollaggio: nelle sessioni solo testo le immagini incollate si convertono automaticamente in percorsi file all'invio e vengono renderizzate di nuovo nel transcript, così non inciampano mai nell'ammissione delle immagini. Porta la tua DASHSCOPE_API_KEY; endpoint/modello/budget configurabili, client HTTP a prova di redirect, funziona in ogni agent preset.

Visione su richiesta per i modelli DeepSeek solo testo: carichi le immagini e il modello chiama uno strumento view_image basato su qualsiasi endpoint di visione compatibile OpenAI (Qwen/DashScope per impostazione predefinita).